跳到主要內容

臺灣博碩士論文加值系統

(18.206.76.226) 您好!臺灣時間:2021/07/30 23:28
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:蔡信宏
研究生(外文):Shin-Hung Tsai
論文名稱:一個應用於訊號分離的獨立成份分析電路之研製
論文名稱(外文):An Independent Component Analysis(ICA) Circuit Design with Its Applications to Signal Separation
指導教授:陳思文陳思文引用關係
指導教授(外文):Szi-Wen Chen
學位類別:碩士
校院名稱:長庚大學
系所名稱:電子工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2007
畢業學年度:95
語文別:中文
論文頁數:53
中文關鍵詞:數位訊號處理屏蔽訊號源分離獨立成份分析演算法即時架構
外文關鍵詞:DSPBlind Source Separation (BSS)Independent Component Analysis (ICA)real-time architecture
相關次數:
  • 被引用被引用:3
  • 點閱點閱:215
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
獨立成份分析(ICA)法是近年來所開發出用以解決屏蔽訊號源分離 (Blind Source Separation,BSS)問題的一種新式演算法。該演算法的特色是其可以在訊號源的混合係數比例未知的情況下,直接分離混合訊號而還原出原始之獨立訊號源,因此ICA演算法在數位訊號處理的相關領域中自有其重要性。本研究則是以extend infomax ICA演算法為基礎,利用硬體描述語言(Verilog)實現出一個針對super- Gaussian 訊號源做分離的即時硬體架構。對於所開發的即時架構,選擇心電混合訊號分別對其做軟體及硬體的模擬,以驗證此架構的正確性。實驗結果證實,此一即時架構的研製將可成功應用於生醫混合訊號分離;此外,本電路也可進一步整合至嵌入式系統相關的應用上。
Independent Component Analysis (ICA) is known as a novel algorithm which is developed to solve the blind signal source (BBS) problems. The characteristic of the algorithm is that it allows a direct separation for a number of mixed signals with unknown coefficients of mixture. Therefore, the ICA algorithm becomes important in the field of the digital signal processing (DSP). This thesis research aims to design and implement a real-time hardware architecture of the extend infomax ICA algorithm that can separate the super-Gaussian signal sources using the Verolig Hardware Description Language (Verilog HDL). To validate the architecture, a number of mixed measured ECG signals were selected in this study for software and hardware simulations. According to our numerical and physical experimental results, the real-time architecture may be successfully applied to separating mixed medical signals into independent sources. Moreover, the designed architecture may be further integrated into an embedded system.
指導教授推薦書...........................................
口試委員會審定書.........................................
授權書.................................................. iii
致謝.................................................... iv
中文摘要.................................................v
英文摘要.................................................vi
目錄.................................................... vii
圖目錄.................................................. x
表目錄................................................. xii
第一章 緒論............................................ 1
1.1研究動機與目的.................................... 1
1.2 ICA研究背景與歷史................................ 2
1.3論文架構.......................................... 7
第二章 獨立成份分析法原理探討.......................... 9
2.1前言.............................................. 9
2.2 ICA演算法........................................ 9
2.2.1 ICA演算法架構............................... 9
2.2.2 ICA演算法基本假設...........................11
2.3 Infomax ICA 演算法................................ 11
2.3.1前言......................................... 11
2.3.2 Infomax ICA原理說明......................... 12
2.4 Extend Infomax ICA演算法........................... 15
2.4.1前言......................................... 15
2.4.2訓練法則..................................... 15
2.4.2.1Extend Infomax ICA在Sub-Gaussian模式..... 17
2.4.2.2Extend Infomax ICA在Super-Gaussian模式.... 19
2.5總結............................................... 20
第三章 ICA即時架構與軟體模擬........................... 21
3.1前言............................................... 21
3.2即時架構設計....................................... 21
3.3軟體模擬結果....................................... 23
3.4矩陣乘法器──利用Systolic Array..................... 27
3.5 CORDIC電路.......................................30
3.5.1前言........................................ 30
3.5.2 CORDIC演算法.............................. 32
3.5.3 CORDIC電路硬體設計........................ 36
3.5.4 CORDIC電路模擬結果........................ 39
第四章 ICA電路實驗結果.................................41
4.1前言...............................................41
4.2 ICA電路運作流程...................................41
4.3 電路合成與比較................................... 44
4.4 硬體模擬..........................................47
4.4.1模擬環境設定................................47
4.4.2硬體模擬結果與效能評估......................48
第五章 結論與未來工作..................................52
參考文獻................................................53
[1] M.Jordan, M.Kearns and S. Solla (Eds), “Extend ICA Removes Artifacts from Electroncephalographic Recording Advance in Neural Information Processing Systems 10, ” MIT Press, Cambridge MA,10:894-900,1998.
[2] A. Hyvärinen, J. Karhunen, and O, Erkki, “Independent Component analysis,” John Wiley and Sons, 2001.
[3] A. Hyvärinen, “Fast and robust fixed-point algorithm for independent component analysis,” IEEE Transaction of neural networks, Vol.10, No.3 1999.
[4] A. J. Bell, and T. J. Sejnowski ,“An information-maximization approach to blind separation and blind deconvolution,” Neural Computation, 7:1129–1159, 1995.
[5] T. -W. Lee, M. Girolsmi, and T. J. Sejnowski, “Independent component analysis using an extended infomax algorithm for mixed sub-Gaussian and super-Gaussian sources,” Neural Computation, 11(2): 417-441, 1999.
[6] K. S. Cho and S. Y. Lee, “Implementation of infomax ICA Algorithm with analog CMOS circuits,” in Proc. Int. Workshop Independent Component Analysis and Blind Signal Separation, San Diego, CA, Dec. 2001.
[7] Chang-Min Kim, Hyung-Min Park, Taesu Kim, Yoon-Kyung Choi, and Soo-Young Lee “FPGA Implementation of ICA Algorithm for Blind Signal Separation and Adaptive Noise Canceling,” IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 14, NO. 5, SEPTEMBER 2003.
[8] T. -P. Jung, S. Makeig, M.J. McKeown, A. J. Bell, T. -W Lee, and T. J. Sejnowski, “Imaging brain dynamics using independent component analysis,” IEEE Proceedings, Vol.89, Iss.7, pp1107-1122 July 2001.
[9] L. Zhukov, D. Weinstein, and C. Johnson, “Independent component analysis for EEG source localization,” IEEE Engineering in Medicine and Biology Magazine, Vol.19, Iss.3, pp87-96 2000 May-June.
[10] C. F. Beckmann, and S. M. Smith, “Probabilistic independent component analysis for functional magnetic resonance imaging,” IEEE Transactions on Medical Imaging, Vol.23, Iss.2, pp.137-152. Feb. 2004.
[11] M. S. Bartlett, J. R. Movellan and T. J. Sejnowski, “Face recognition by independent component analysis,” IEEE Trans on Neural Network, vol.13, no.6, November 2002.
[12] 游世凱“獨立成份分析(ICA)電路架構設計與實現-應用於醫學訊號處理,”長庚大學醫療機電工程研究所碩士論文 ,2004年.
[13] S. Amari, A. Cichcki, and H. Yang, “A new learning algorithm for blind signal separation,” Advances in neural information processing systems, pp.757-763
[14] J. -F. Cardoso, “ Blind signal separation: Statistical principles,” Proceedings of IEEE, 86(10), 2009–2025, 1998.
[15] H.T. Kunga and C.E. Leiserson, “Systolic arrays for VLSI,” in Sparse Matrix Symposium, SIAM, pp.256–282,1978.
[16] P. K. Keshab, “VLSI digital signal processing systems,” John Wiley and Sons, 1999.
[17] Ray Andraka, “A survey of CORDIC algorithms for FPGA based computers,” Andraka Consulting Group, Inc.
[18] Y. H. Hu., “CORDIC-based VLSI architecture for digital signal processing,” IEEE Signal Processing magazine, 1992.
[19]黃朝金 “利用CORDIC原理實現可預測旋轉方向之SIN-COS產生器及其FPGA實作,”中山大學資訊工程學系研究所碩士論文, 2000年.
[20] S. Lee, “Design of Computer and Other Complex Digital Devices,” Prentice Hall,1999.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top